Re-ranking search results using semantic similarity

In this paper, we propose a re-ranking method which employs semantic similarity to improve the quality of search results. We fetch the top N results returned by search engine, and use semantic similarities between the candidate and the query to re-rank the results. We first convert the ranking position to an importance score for each candidate. Then we combine the semantic similarity score with this initial importance score and finally we get the new ranks. In the experiment, we use NDCG to evaluate the re-ranking results and the experimental results validate that our proposed method can indeed improve the search performance and meet users' need to a certain extent.